Related papers: RegaVAE: A Retrieval-Augmented Gaussian Mixture Va…
A major challenge in quantum computing is its application to large real-world datasets due to scarce quantum hardware resources. One approach to enabling tractable quantum models for such datasets involves finding low-dimensional…
Data augmentation effectively addresses the imbalanced-small sample data (ISSD) problem in hyperspectral image classification (HSIC). While most methodologies extend features in the latent space, few leverage text-driven generation to…
The variational autoencoder (VAE) framework remains a popular option for training unsupervised generative models, especially for discrete data where generative adversarial networks (GANs) require workaround to create gradient for the…
Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still…
Given the growing trend of many organizations integrating Retrieval Augmented Generation (RAG) into their operations, we assess RAG on domain-specific data and test state-of-the-art models across various optimization techniques. We…
A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to inaccurate amortized…
This technical report details a novel approach to combining reasoning and retrieval augmented generation (RAG) within a single, lean language model architecture. While existing RAG systems typically rely on large-scale models and external…
This paper presents a comprehensive study of Retrieval-Augmented Generation (RAG), tracing its evolution from foundational concepts to the current state of the art. RAG combines retrieval mechanisms with generative language models to…
Generative models have recently started to outperform extractive models in Open Domain Question Answering, largely by leveraging their decoder to attend over multiple encoded passages and combining their information. However, generative…
Large language models (LLMs) augmented with retrieval exhibit robust performance and extensive versatility by incorporating external contexts. However, the input length grows linearly in the number of retrieved documents, causing a dramatic…
The natural language generation domain has witnessed great success thanks to Transformer models. Although they have achieved state-of-the-art generative quality, they often neglect generative diversity. Prior attempts to tackle this issue…
The rapid evolution of mobile edge computing (MEC) has introduced significant challenges in optimizing resource allocation in highly dynamic wireless communication systems, in which task offloading decisions should be made in real-time.…
Learning robust representations of authorial style is crucial for authorship attribution and AI-generated text detection. However, existing methods often struggle with content-style entanglement, where models learn spurious correlations…
Variational Autoencoders (VAEs) typically rely on a probabilistic decoder with a predefined likelihood, most commonly an isotropic Gaussian, to model the data conditional on latent variables. While convenient for optimization, this choice…
Variational autoencoders (VAE) are powerful generative models that learn the latent representations of input data as random variables. Recent studies show that VAE can flexibly learn the complex temporal dynamics of time series and achieve…
Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or domain-specific knowledge. Nonetheless, current models still produce closed-domain…
Multi-label classification (MLC) is a prediction task where each sample can have more than one label. We propose a novel contrastive learning boosted multi-label prediction model based on a Gaussian mixture variational autoencoder…
Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood. In particular, it is commonly believed that Gaussian encoder/decoder…
Large Language Models (LLMs) are widely used in critical fields such as healthcare, education, and finance due to their remarkable proficiency in various language-related tasks. However, LLMs are prone to generating factually incorrect…
Probabilistic generative models are attractive for scientific modeling because their inferred parameters can be used to generate hypotheses and design experiments. This requires that the learned model provide an accurate representation of…